© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 17734
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     każdej
    -0.26
    åħĢ
    -0.25
    orus
    -0.25
    Interpolator
    -0.25
    åĪ®
    -0.25
    orama
    -0.25
    AndWait
    -0.25
    AYER
    -0.24
    wed
    -0.24
    å¨ħ
    -0.24
    POSITIVE LOGITS
    .setFill
    0.27
    HEME
    0.26
    ÑģеÑĤ
    0.26
    豨
    0.26
    _TC
    0.26
    TC
    0.26
    fine
    0.26
     ÐŁÑĢе
    0.25
    lico
    0.25
    pass
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.